cocos-creator-3x-cn

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill's instructions and reference materials are focused entirely on technical guidance. There are no attempts to override safety filters, bypass constraints, or extract internal configuration data.
  • [DATA_EXFILTRATION]: No sensitive local file paths (e.g., SSH keys, cloud credentials) or data harvesting patterns were detected. Resource loading examples use official Cocos Creator APIs with placeholder URLs for illustrative purposes.
  • [REMOTE_CODE_EXECUTION]: No unauthorized script execution or remote package installations are present. The skill provides documentation for standard asset-management features such as assetManager.loadRemote and loadBundle using well-known engine patterns.
  • [OBFUSCATION]: All code and documentation are provided in clear, human-readable text. No zero-width characters, homoglyphs, or multi-layer encoding (e.g., Base64) were found.
  • [PRIVILEGE_ESCALATION]: The skill does not include any commands for acquiring elevated system permissions, such as sudo or administrative modifications.
  • [SAFE]: The skill is a legitimate development assistant that aligns with Cocos Creator 3.8 LTS official documentation and best practices for TypeScript game development.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 12:05 PM